TY - GEN
T1 - Water Quality Estimation from IoT Sensors Using a Meta-ensemble
AU - Davrazos, Gregory
AU - Panagiotakopoulos, Theodor
AU - Kotsiantis, Sotiris
N1 - Publisher Copyright:
© 2023, IFIP International Federation for Information Processing.
PY - 2023
Y1 - 2023
N2 - Water quality estimation using machine learning is a type of data analysis process that uses algorithms to identify patterns in large sets of data related to water quality. This can include identifying pollutants and other potential contamination that could negatively impact quality for drinking purposes, recreational activities or other uses. This helps ensure that the safety of water sources and the quality of recreational activities are constantly monitored and maintained. Thus, in this paper, a set of existing machine learning classifiers is applied to Internet of Things (IoT) sensor data on various water quality parameters, and the results are compared. Subsequently, a meta ensemble classifier that utilizes the soft voting technique of the best four previous classifiers is proposed to enhance estimation accuracy. According to results on the majority of the metrics used, this meta ensemble classifier outperforms all previously considered classifiers.
AB - Water quality estimation using machine learning is a type of data analysis process that uses algorithms to identify patterns in large sets of data related to water quality. This can include identifying pollutants and other potential contamination that could negatively impact quality for drinking purposes, recreational activities or other uses. This helps ensure that the safety of water sources and the quality of recreational activities are constantly monitored and maintained. Thus, in this paper, a set of existing machine learning classifiers is applied to Internet of Things (IoT) sensor data on various water quality parameters, and the results are compared. Subsequently, a meta ensemble classifier that utilizes the soft voting technique of the best four previous classifiers is proposed to enhance estimation accuracy. According to results on the majority of the metrics used, this meta ensemble classifier outperforms all previously considered classifiers.
KW - Internet of Things
KW - Machine learning
KW - Meta Ensemble
KW - Soft voting
KW - Water quality
UR - http://www.scopus.com/inward/record.url?scp=85164001560&partnerID=8YFLogxK
U2 - 10.1007/978-3-031-34171-7_32
DO - 10.1007/978-3-031-34171-7_32
M3 - Conference contribution
AN - SCOPUS:85164001560
SN - 9783031341700
T3 - IFIP Advances in Information and Communication Technology
SP - 393
EP - 403
BT - Artificial Intelligence Applications and Innovations. AIAI 2023 IFIP WG 12.5 International Workshops - MHDW 2023, 5G-PINE 2023, ΑΙBMG 2023, and VAA-CP-EB 2023, Proceedings
A2 - Maglogiannis, Ilias
A2 - Iliadis, Lazaros
A2 - Papaleonidas, Antonios
A2 - Chochliouros, Ioannis
PB - Springer Science and Business Media Deutschland GmbH
T2 - 19th IFIP WG 12.5 International Conference on Artificial Intelligence Applications and Innovations, AIAI 2023
Y2 - 14 June 2023 through 17 June 2023
ER -